© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15559
    Prev
    Next
    INDEX
    Explanations

    terms related to components and mechanisms in engineering or technical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setOnAction
    -0.49
     Obrador
    -0.49
    MENAFN
    -0.48
    mirante
    -0.48
    gheny
    -0.48
     AllMovie
    -0.48
    出版年
    -0.48
     intended
    -0.47
    Външни
    -0.47
     ),
    -0.46
    POSITIVE LOGITS
    Хьажоргаш
    0.69
     fraî
    0.68
    FormTagHelper
    0.63
    DockStyle
    0.60
     CreateTagHelper
    0.57
    الإنجليزية
    0.56
     prochaines
    0.56
     prossima
    0.55
     incluem
    0.55
    protoc
    0.54
    Activations Density 0.057%

    No Known Activations